Speaker
：游佳龍
ID
：
19967034
Date
：
11/24/2010
National Taiwan Ocean University
Department of Communications, Navigation and
Control Engineering
Outline
Abstract
Introduction
The extended BAM Neural Network Model
Proof of the New Model’s Stability
Experiment Results
Abstract
In this paper we propose an extended bidirectional associative
memory (BAM) neural network model which can do auto

and
hetero

associative memory. The theoretical proof for this neural
network model’s stability is given. Experiments show that this
neural network model is much more powerful than the M

P
Model, Discrete Hopfield Neural Network, Continuous
Hopfield Neural Network, Discrete Bidirectional Associative
Memory Neural Network, Continuous and Adaptive
Bidirectional Associative Memory Neural Network, Back

Propagation Neural Network and Optimal Designed Nonlinear
Continuous Neural Network. Experimental results also show
that, when it does auto

associative memory, the power of this
model is the same as the Loop Neural Network Model which
can only do auto

associative memory.
Introduction
Associative
memory
is
an
important
part
in
neural
network
theory
and
it
is
also
an
efficient
function
in
the
applications
of
intelligent
control,
pattern
recognition
and
artificial
intelligence
.
At
present,
many
neural
network
models
such
as
Loop
model,
M

P
model,
Discrete
and
Continuous
Hopfield
Model,
Kosko’s
Discrete
BAM,
Optimal
Designed
Nonlinear
Continuous
Neural
Network,
etc
.
,
which
can
do
associative
memory,
have
existed
.
Each
model
has
its
own
advantages
and
disadvantages
.
Introduction
In practical applications, the more powerful the
network is, the better the associative memory result
are. One important task is to find or construct a
powerful associative neural network. The so

called
neural network model has two meanings, that is its
structure and its training algorithm.
In this paper we propose an extended bidirectional
associative memory(BAM) neural network model.
The reason why we call this new model an extended
BAM neural network model is that its structure is the
same as the BAM model. The different between the
BAM and the extended BAM is the training algorithm.
The extended BAM
Neural Network Model
This part introduces the architecture and learning
algorithm for the Extended. This model can be used to
carry out both auto

associative memory and hetero

associative memory. The BAM model(Kosk0 Model)
is a memory consisting of two layers. It uses the
forward and backward information flow to produce an
associative search for stored stimulus

response
association
.
The extended BAM
Neural Network Model
The extended BAM
Neural Network Model
The firing function for both 1ayers:neuron is
Consider the stored association pairs as
The formula for the weight matrix is
For our extended BAM model, the learning algorithm
is Delta Learning Rule.
Delta learning rule
During training we treat this two layer network as a
feedforward neural network, and the activation function for
output layer's neurons is sigmoid function.
After the training is finished, we use the following activation
function in both layers to do associative memory.
By this training method the forward connection weight matrix
M can be obtained. We use
M
as the backward connection
weight matrix.
The extended BAM
Neural Network Model
Proof of the New Model’s
Stability
We can define the energy function as
Since we get the energy
function equivalent form as follows
The energy change due to the state change
of a is
Proof of the New Model’s
Stability
By the BAM theorem
has only three values, i.e.,

2,0 and 2. If , we have
So,
and
So, we have This is
the situation of zero change in and we don’t consider this
case. The energy change due to the state change of
is the same as . Hence along discrete trajectories
as claimed.
Proof of the New Model’s
Stability
Since E is bounded below
the associative memory of the extended BAM converges
to some stable points, meaning that, the network is stable.
Experiment Result
The experiment results show that the New Model is much
more powerful than the other models to carry out
associative memory.
In our experiment the network consists of 8 processing
units(neurons) for each layer. The set of vector pairs to
be stored is
The experiments are carried out in the following four
cases.
Experiment Result
Experiment Result
Experiment Result
Using the same method as above, we get the following
results.
References
Comments 0
Log in to post a comment